Recently, domain adaptation, a form of transfer learning, has been extensively applied to mechanical fault diagnosis across diverse operating conditions to address the challenges of insufficient labeled data and frequent operational state transitions. However, most existing approaches focus solely on the spatial distribution of inter-domain categorical features, neglecting the clustering properties of feature clusters. Moreover, most pseudo-labeling approaches lack a rational screening mechanism based on the quality of the pseudo-labels. To address these challenges, this paper proposes a Dynamic Pseudo-Label Guided Adversarial Multi-Scale Graph Convolutional Network (DPAMGCN) for unsupervised cross-domain fault diagnosis. First, a network architecture is designed by cascading a multi-scale parallel Convolutional Neural Network (CNN) with a multi-receptive-field graph convolutional network (MRF-GCN) to extract features. Second, a multi-objective total-loss function is constructed that integrates geometric loss with three standard loss functions to jointly optimize feature clustering and spatial distribution. Finally, a dynamic threshold-based pseudo-label filtering strategy is proposed that, when combined with a geometric loss, enhances the model's generalization capability. Cross-domain transfer experiments conducted on the University of Ottawa (Ottawa) and Huazhong University of Science and Technology (HUST) benchmark datasets demonstrate that DPAMGCN achieves outstanding cross-domain diagnostic performance under the proposed optimization strategy and pseudo-label screening mechanism.
Jinqi Gao, Bo Zhang, Tianlong Huo et al.· Review of Scientific Instrum...· 0 citations
To address the issue that intelligent fault diagnosis models for rolling bearings are susceptible to the effects of load and speed variations, as well as shifts in data distribution, when applied across different operating conditions, this paper proposes a fault diagnosis domain generalization method that combines mean difference constraints with domain adversarial learning. Taking raw one-dimensional vibration signals as input, this method first employs a multiscale one-dimensional convolutional network to extract fault impact features and periodic features across different time scales; Subsequently, mean difference constraints between source domains are introduced in the feature space to reduce the offset in the centers of feature distributions across different source operating conditions; simultaneously, a domain-adversarial discriminator based on gradient inversion layers is constructed to weaken the operating condition discriminative information in the feature representations, thereby prompting the model to learn domain-invariant features that possess both fault class discriminability and operating condition insensitivity. Experiments were conducted using two rolling bearing datasets from Case Western Reserve University (CWRU) and Paderborn University (PU) to establish a leave-one-out cross-condition diagnosis task. The results show that the proposed method achieves an average accuracy of 99.08% ± 0.19% on the CWRU dataset, and an average accuracy of 91.86% ± 0.34% on the PU dataset, both outperforming comparison methods such as SVM, 1D-CNN, ResNet1D, TCN, CORAL, MMD, and DANN. Furthermore, a Welch’s t-test based on summary statistics indicates that the improvement over the best baseline method is statistically significant. Ablation experiments and parameter sensitivity analysis further validate the effectiveness of multiscale feature extraction, mean difference constraints, and domain adversarial learning in enhancing the model’s generalization capability across different operating conditions.
Jiabing Zhou, Xiang Gu, Bo Zhang et al.· Advanced Engineering&Pre...· 0 citations
To address the insufficient generalization capability of rolling bearing fault diagnosis models under complex operating conditions such as variable rotational speed, variable load, and variable radial force, this paper proposes a domain generalization fault diagnosis method based on Mamba feature extraction and causal generalization loss. First, the raw vibration signals are standardized and segmented using a sliding window strategy. Then, the selective state space model Mamba is employed to model long-range temporal dependencies and local dynamic variations in fault impact signals. Subsequently, from the perspective of causal invariance, generalization constraints are constructed by treating stable representations related to fault categories as causal features, while regarding amplitude variations, noise disturbances, and speed fluctuations induced by operating-condition changes as non-causal factors. A causal generalization loss consisting of class-conditional causal prototype consistency loss and feature decoupling regularization is designed to enhance the model’s adaptability to unseen operating conditions. Experiments are conducted on the Paderborn University (PU) and JNU datasets, where four operating conditions are regarded as four domains to construct cross-condition diagnosis tasks under a leave-one-condition-out evaluation protocol. The proposed method is compared with support vector machine (SVM), one-dimensional convolutional neural network (1D-CNN), one-dimensional residual network (ResNet1D), temporal convolutional network (TCN), correlation alignment (CORAL), domain-adversarial neural network (DANN), maximum mean discrepancy (MMD), and vanilla Mamba. Experimental results show that the proposed method achieves an average accuracy of 93.56% on the PU dataset and 96.28% on the JNU dataset, outperforming all comparison methods and further demonstrating its effectiveness.
Jiabing Zhou, Xiang Gu, Bo Zhang et al.· Advanced Engineering&Pre...· 0 citations
A novel joint hierarchical suppression framework is developed, which collaboratively operates on channel and spatial dimensions under domain label supervision to identify and remove domain-specific features in shallow network layers and is embedded into fully connected layers to drive the model to learn residual domain-invariant features, thus greatly boosting generalization performance.
Tianlong Huo, Rongzhen Zhao, Jun Gong et al.· Structural Health Monitoring· 0 citations